Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting cues in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Our
    -0.22
     Whilst
    -0.22
     We
    -0.21
     whilst
    -0.20
    Our
    -0.18
     ourselves
    -0.18
     Please
    -0.17
     our
    -0.17
    .Our
    -0.16
     ÐľÑĭ
    -0.16
    POSITIVE LOGITS
     Officials
    0.23
    Officials
    0.23
     officials
    0.22
     Gov
    0.19
     Asked
    0.19
     About
    0.19
    That
    0.19
     "(
    0.18
    Asked
    0.18
    But
    0.18
    Act Density 0.283%

    No Known Activations